EUVIMEDEUVIMED entdecken
Crossref

3D Breast Cancer Segmentation in DCE‐MRI Using Deep Learning With Weak Annotation

Ga Eun Park, Sung Hun Kim iD, Yoonho Nam iD, Junghwa Kang, Minjeong Park, Bong Joo Kang

Journal of Magnetic Resonance Imaging · 2024

DOI: 10.1002/jmri.28960 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2024. Verfasst von Ga Eun Park und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Breast Neoplasms, Magnetic Resonance Imaging, Imaging, Three-Dimensional. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 34 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Deep learning models require large‐scale training to perform confidently, but obtaining annotated datasets in medical imaging is challenging. Weak annotation has emerged as a way to save time and effort.

Purpose

To develop a deep learning model for 3D breast cancer segmentation in dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) using weak annotation with reliable performance. Study Type Retrospective. Population Seven hundred and thirty‐six women with breast cancer from a single institution, divided into the development ( N = 544) and test dataset ( N = 192). Field Strength/Sequence 3.0‐T, 3D fat‐saturated gradient‐echo axial T1‐weighted flash 3D volumetric interpolated brain examination (VIBE) sequences. Assessment Two radiologists performed a weak annotation of the ground truth using bounding boxes. Based on this, the ground truth annotation was completed through autonomic and manual correction. The deep learning model using 3D U‐Net transformer (UNETR) was trained with this annotated dataset. The segmentation results of the test set were analyzed by quantitative and qualitative methods, and the regions were divided into whole breast and region of interest (ROI) within the bounding box. Statistical Tests As a quantitative method, we used the Dice similarity coefficient to evaluate the segmentation result. The volume correlation with the ground truth was evaluated with the Spearman correlation coefficient. Qualitatively, three readers independently evaluated the visual score in four scales. A P ‐value

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBreast NeoplasmsMagnetic Resonance ImagingImaging, Three-DimensionalContrast MediaHumansFemaleRetrospective StudiesMiddle AgedAdultAgedReproducibility of ResultsImage Interpretation, Computer-AssistedBreastImage Processing, Computer-Assisted

Stichwörter der Autor:innen

breast cancerdeep learningsegmentation

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
  • Division of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin, Republic of Korea.

ORCID-Profile: Sung Hun Kim, Yoonho Nam

Zitieren

APA

Park, G. E., Kim, S. H., Nam, Y., Kang, J., Park, M., & Kang, B. J. (2024). 3D Breast Cancer Segmentation in DCE‐MRI Using Deep Learning With Weak Annotation. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.28960

Vancouver

Park GE, Kim SH, Nam Y, Kang J, Park M, Kang BJ. 3D Breast Cancer Segmentation in DCE‐MRI Using Deep Learning With Weak Annotation. Journal of Magnetic Resonance Imaging. 2024. doi:10.1002/jmri.28960

BibTeX
@article{Park2024,
  author = {Park, Ga Eun and Kim, Sung Hun and Nam, Yoonho and Kang, Junghwa and Park, Minjeong and Kang, Bong Joo},
  title = {3D Breast Cancer Segmentation in DCE‐MRI Using Deep Learning With Weak Annotation},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2024},
  doi = {10.1002/jmri.28960}
}
Kostenlos starten →